
!pip install pmdarima

Collecting pmdarima
  Downloading pmdarima-2.0.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl (1.9 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.9/1.9 MB 31.1 MB/s eta 0:00:00a 0:00:01
Requirement already satisfied: joblib>=0.11 in /opt/conda/miniconda3/lib/python3.8/site-packages (from pmdarima) (1.2.0)
Requirement already satisfied: statsmodels>=0.13.2 in /opt/conda/miniconda3/lib/python3.8/site-packages (from pmdarima) (0.13.2)
Requirement already satisfied: urllib3 in /opt/conda/miniconda3/lib/python3.8/site-packages (from pmdarima) (1.25.11)
Collecting numpy>=1.21.2
  Downloading numpy-1.23.5-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (17.1 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 17.1/17.1 MB 66.7 MB/s eta 0:00:0000:0100:01
Requirement already satisfied: scikit-learn>=0.22 in /opt/conda/miniconda3/lib/python3.8/site-packages (from pmdarima) (0.24.2)
Requirement already satisfied: Cython!=0.29.18,!=0.29.31,>=0.29 in /opt/conda/miniconda3/lib/python3.8/site-packages (from pmdarima) (0.29.32)
Requirement already satisfied: setuptools!=50.0.0,>=38.6.0 in /opt/conda/miniconda3/lib/python3.8/site-packages (from pmdarima) (59.8.0)
Requirement already satisfied: pandas>=0.19 in /opt/conda/miniconda3/lib/python3.8/site-packages (from pmdarima) (1.2.5)
Requirement already satisfied: scipy>=1.3.2 in /opt/conda/miniconda3/lib/python3.8/site-packages (from pmdarima) (1.6.3)
Requirement already satisfied: python-dateutil>=2.7.3 in /opt/conda/miniconda3/lib/python3.8/site-packages (from pandas>=0.19->pmdarima) (2.8.0)
Requirement already satisfied: pytz>=2017.3 in /opt/conda/miniconda3/lib/python3.8/site-packages (from pandas>=0.19->pmdarima) (2022.6)
Requirement already satisfied: threadpoolctl>=2.0.0 in /opt/conda/miniconda3/lib/python3.8/site-packages (from scikit-learn>=0.22->pmdarima) (3.1.0)
  Downloading numpy-1.22.4-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (16.9 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 16.9/16.9 MB 65.0 MB/s eta 0:00:0000:0100:01
Requirement already satisfied: packaging>=21.3 in /opt/conda/miniconda3/lib/python3.8/site-packages (from statsmodels>=0.13.2->pmdarima) (21.3)
Requirement already satisfied: patsy>=0.5.2 in /opt/conda/miniconda3/lib/python3.8/site-packages (from statsmodels>=0.13.2->pmdarima) (0.5.3)
Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in /opt/conda/miniconda3/lib/python3.8/site-packages (from packaging>=21.3->statsmodels>=0.13.2->pmdarima) (2.4.7)
Requirement already satisfied: six in /opt/conda/miniconda3/lib/python3.8/site-packages (from patsy>=0.5.2->statsmodels>=0.13.2->pmdarima) (1.16.0)
Installing collected packages: numpy, pmdarima
  Attempting uninstall: numpy
    Found existing installation: numpy 1.19.5
    Uninstalling numpy-1.19.5:
      Successfully uninstalled numpy-1.19.5
ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
pointpats 2.2.0 requires opencv-contrib-python>=4.2.0, which is not installed.
pysal 2.4.0 requires urllib3>=1.26, but you have urllib3 1.25.11 which is incompatible.
Successfully installed numpy-1.22.4 pmdarima-2.0.2
WARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv


!pip install --upgrade numpy

Requirement already satisfied: numpy in /opt/conda/miniconda3/lib/python3.8/site-packages (1.22.4)
Collecting numpy
  Using cached numpy-1.23.5-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (17.1 MB)
Installing collected packages: numpy
  Attempting uninstall: numpy
    Found existing installation: numpy 1.22.4
    Uninstalling numpy-1.22.4:
      Successfully uninstalled numpy-1.22.4
ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
pointpats 2.2.0 requires opencv-contrib-python>=4.2.0, which is not installed.
scipy 1.6.3 requires numpy<1.23.0,>=1.16.5, but you have numpy 1.23.5 which is incompatible.
pysal 2.4.0 requires urllib3>=1.26, but you have urllib3 1.25.11 which is incompatible.
Successfully installed numpy-1.23.5
WARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv
Note: you may need to restart the kernel to use updated packages.


from pyspark import SparkContext, SparkConf
from pyspark.sql import SparkSession
from google.cloud import storage
from pyspark.sql.functions import lit
from functools import reduce
from pyspark.sql import DataFrame
from pyspark.sql.functions import *
from datetime import datetime
from statsmodels.tsa.stattools import adfuller
from statsmodels.tsa.seasonal import seasonal_decompose
from statsmodels.tsa.arima.model import ARIMA
from pmdarima.arima import auto_arima
from pyspark.sql.window import Window

import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline


spark = SparkSession.builder.appName('Nifty50').getOrCreate()

#change configuration settings on Spark 
/gateway/default/node/conf?host&port = spark.sparkContext._conf.setAll([('spark.executor.memory', '30g'), ('spark.app.name', 'Spark Updated Conf'), ('spark.executor.cores', '4'), ('spark.cores.max', '4'), ('spark.driver.memory','30g'), ("spark.driver.maxResultSize", "70g")])

gcs_client = storage.Client()


bucket_name = 'new_bigdata_nifty50'


bucket = gcs_client.bucket(bucket_name)


file_name = 'df_with_indicators.csv'


df = spark.read.csv('gs://{}//{}'.format(bucket_name, file_name), inferSchema=True)


new_columns = ['date',
 'close',
 'high',
 'low',
 'open',
 'volume',
 'sma5',
 'sma10',
 'sma15',
 'sma20',
 'ema5',
 'ema10',
 'ema15',
 'ema20',
 'upperband',
 'middleband',
 'lowerband',
 'HT_TRENDLINE',
 'KAMA10',
 'KAMA20',
 'KAMA30',
 'SAR',
 'TRIMA5',
 'TRIMA10',
 'TRIMA20',
 'ADX5',
 'ADX10',
 'ADX20',
 'APO',
 'CCI5',
 'CCI10',
 'CCI15',
 'macd510',
 'macd520',
 'macd1020',
 'macd1520',
 'macd1226',
 'MFI',
 'MOM10',
 'MOM15',
 'MOM20',
 'ROC5',
 'ROC10',
 'ROC20',
 'PPO',
 'RSI14',
 'RSI8',
 'slowk',
 'slowd',
 'fastk',
 'fastd',
 'fastksr',
 'fastdsr',
 'ULTOSC',
 'WILLR',
 'ATR',
 'Trange',
 'TYPPRICE',
 'HT_DCPERIOD',
 'BETA',
 'sector',
 'company',
 'Inflation Rate ',
 'Balance of Trade',
 'Bank Lending Rate',
 'Car Registrations',
 'Consumer Price Index',
 'Crude Oil Production',
 'Fiscal Expenditure',
 'Industrial Production',
 'Food Inflation',
 'Producer Prices',
 'Reverse Repo Rate',
 'Steel Production',
 'Tourist Arrivals',
 'Corporate Tax Rate ',
 'Export Prices',
 'GDP per Capita PPP',
 'GDP',
 'Gross National Product',
 'Import Prices',
 'Military Expenditure']


from functools import reduce

old_columns = df.schema.names
df = reduce(lambda data, idx: data.withColumnRenamed(old_columns[idx], new_columns[idx]), range(len(old_columns)), df)


cols = df.columns
cols.remove('company')
cols.remove('sector')

exprs = {x: "avg" for x in cols}
exprs['sector'] = 'first'
date_df = df.groupby(df.company, to_date(df.date).alias('day')).agg(exprs)


cols = df.columns
cols.remove('company')
cols.remove('sector')

exprs = {x: "avg" for x in cols}
exprs['sector'] = 'first'
date_df = df.groupby(df.company, to_date(df.date).alias('day')).agg(exprs)


w = Window.partitionBy('company').orderBy("day")
date_df = date_df.withColumn('diffClose', col("avg(close)") - lag(col("avg(close)")).over(w))


sum_df = date_df.groupby(df.company).agg(sum('diffClose').alias('totalChange'), first('first(sector)').alias('sector'))


w = Window.partitionBy('sector')
sector_df = sum_df.withColumn('maxtotalChange', max('totalChange').over(w))\
        .where(col('totalChange') == col('maxtotalChange'))\
        .drop('maxtotalChange')


sector_df = sector_df.toPandas()


top_companies_per_sector = list(sector_df['company'])
top_companies_per_sector.remove('NIFTY 50')
top_companies_per_sector.remove('NIFTY BANK')
top_companies_per_sector

['INDIGO',
 'ADANIENT',
 'MARUTI',
 'BHARTIARTL',
 'BAJFINANCE',
 'APOLLOHOSP',
 'ADANIGREEN',
 'LTI',
 'SHREECEM',
 'NESTLEIND',
 'SIEMENS',
 'LT',
 'RELIANCE',
 'DMART',
 'DLF',
 'PIIND',
 'ASIANPAINT']


top_companies_df = date_df.filter(date_df.company.isin(top_companies_per_sector)).toPandas()


import pandas as pd
def test_stationarity(timeseries, company):
    #Determing rolling statistics
    rolmean = timeseries.rolling(12).mean()
    rolstd = timeseries.rolling(12).std()
    #Plot rolling statistics:
    plt.plot(timeseries, color='blue',label='Original')
    plt.plot(rolmean, color='red', label='Rolling Mean')
    plt.plot(rolstd, color='black', label = 'Rolling Std')
    plt.legend(loc='best')
    plt.title('Rolling Mean and Standard Deviation for {}'.format(company))
    plt.show(block=False)
    
    print("Results of dickey fuller test")
    adft = adfuller(timeseries,autolag='AIC')
    
    output = pd.Series(adft[0:4],index=['Test Statistics','p-value','No. of lags used','Number of observations used'])
    for key,values in adft[4].items():
        output['critical value (%s)'%key] =  values
    print(output)

for company in top_companies_per_sector:
    test_stationarity(top_companies_df[top_companies_df['company']==company]['avg(close)'], company)

Results of dickey fuller test
Test Statistics                  -1.737789
p-value                           0.411755
No. of lags used                  9.000000
Number of observations used    1580.000000
critical value (1%)              -3.434496
critical value (5%)              -2.863371
critical value (10%)             -2.567745
dtype: float64

Results of dickey fuller test
Test Statistics                   2.935496
p-value                           1.000000
No. of lags used                 21.000000
Number of observations used    1747.000000
critical value (1%)              -3.434099
critical value (5%)              -2.863196
critical value (10%)             -2.567652
dtype: float64

Results of dickey fuller test
Test Statistics                  -1.781028
p-value                           0.389921
No. of lags used                  9.000000
Number of observations used    1787.000000
critical value (1%)              -3.434015
critical value (5%)              -2.863159
critical value (10%)             -2.567632
dtype: float64

Results of dickey fuller test
Test Statistics                  -0.201060
p-value                           0.938395
No. of lags used                  1.000000
Number of observations used    1795.000000
critical value (1%)              -3.433998
critical value (5%)              -2.863152
critical value (10%)             -2.567628
dtype: float64

Results of dickey fuller test
Test Statistics                  -0.497503
p-value                           0.892503
No. of lags used                 10.000000
Number of observations used    1786.000000
critical value (1%)              -3.434017
critical value (5%)              -2.863160
critical value (10%)             -2.567632
dtype: float64

Results of dickey fuller test
Test Statistics                   0.338065
p-value                           0.979025
No. of lags used                 18.000000
Number of observations used    1778.000000
critical value (1%)              -3.434033
critical value (5%)              -2.863167
critical value (10%)             -2.567636
dtype: float64

Results of dickey fuller test
Test Statistics                 -0.277376
p-value                          0.928648
No. of lags used                21.000000
Number of observations used    974.000000
critical value (1%)             -3.437082
critical value (5%)             -2.864512
critical value (10%)            -2.568352
dtype: float64

Results of dickey fuller test
Test Statistics                  -0.842076
p-value                           0.806449
No. of lags used                 23.000000
Number of observations used    1433.000000
critical value (1%)              -3.434922
critical value (5%)              -2.863559
critical value (10%)             -2.567845
dtype: float64

Results of dickey fuller test
Test Statistics                  -2.051256
p-value                           0.264561
No. of lags used                  2.000000
Number of observations used    1794.000000
critical value (1%)              -3.434000
critical value (5%)              -2.863152
critical value (10%)             -2.567628
dtype: float64

Results of dickey fuller test
Test Statistics                   0.089650
p-value                           0.965347
No. of lags used                  9.000000
Number of observations used    1787.000000
critical value (1%)              -3.434015
critical value (5%)              -2.863159
critical value (10%)             -2.567632
dtype: float64


import numpy as np
for company in top_companies_per_sector:
    company_log = np.log(top_companies_df[top_companies_df['company']==company]['avg(close)'])
    company_log.index = pd.to_datetime(company_log.index)
    result = seasonal_decompose(company_log,  model='multiplicative', period=1)
    fig = plt.figure(figsize=(16, 9))  
    fig = result.plot()  
    fig.set_size_inches(16, 9)
    fig.suptitle('Sesonal Decompose of Close Price of {}'.format(company))

/tmp/ipykernel_8625/702561032.py:6: RuntimeWarning: More than 20 figures have been opened. Figures created through the pyplot interface (`matplotlib.pyplot.figure`) are retained until explicitly closed and may consume too much memory. (To control this warning, see the rcParam `figure.max_open_warning`).
  fig = plt.figure(figsize=(16, 9))

<Figure size 1600x900 with 0 Axes>

<Figure size 1600x900 with 0 Axes>

<Figure size 1600x900 with 0 Axes>

<Figure size 1600x900 with 0 Axes>

<Figure size 1600x900 with 0 Axes>

<Figure size 1600x900 with 0 Axes>

<Figure size 1600x900 with 0 Axes>

<Figure size 1600x900 with 0 Axes>

<Figure size 1600x900 with 0 Axes>


from statsmodels.tsa.arima.model import ARIMA


top_companies_df.columns

Index(['company', 'day', 'avg(Reverse Repo Rate)', 'avg(RSI14)',
       'avg(Car Registrations)', 'avg(CCI10)', 'avg(TRIMA10)', 'avg(SAR)',
       'avg(fastdsr)', 'avg(ADX20)', 'avg(WILLR)', 'avg(sma10)',
       'avg(macd1226)', 'avg(sma20)', 'avg(ema15)', 'avg(ema10)',
       'avg(KAMA10)', 'avg(TRIMA20)', 'avg(Tourist Arrivals)', 'avg(fastksr)',
       'avg(Steel Production)', 'avg(Gross National Product)', 'avg(TRIMA5)',
       'avg(macd1020)', 'avg(CCI5)', 'avg(MOM15)', 'avg(Export Prices)',
       'avg(TYPPRICE)', 'avg(GDP per Capita PPP)', 'avg(HT_DCPERIOD)',
       'avg(ema5)', 'first(sector)', 'avg(open)', 'avg(Producer Prices)',
       'avg(PPO)', 'avg(ADX10)', 'avg(CCI15)', 'avg(Fiscal Expenditure)',
       'avg(Import Prices)', 'avg(ATR)', 'avg(Crude Oil Production)',
       'avg(upperband)', 'avg(low)', 'avg(BETA)', 'avg(ROC20)', 'avg(macd520)',
       'avg(date)', 'avg(MOM10)', 'avg(fastk)', 'avg(MFI)',
       'avg(Corporate Tax Rate )', 'avg(APO)', 'avg(sma5)', 'avg(KAMA20)',
       'avg(RSI8)', 'avg(macd510)', 'avg(lowerband)',
       'avg(Military Expenditure)', 'avg(sma15)', 'avg(fastd)', 'avg(ADX5)',
       'avg(slowd)', 'avg(ema20)', 'avg(Consumer Price Index)',
       'avg(Industrial Production)', 'avg(KAMA30)', 'avg(GDP)',
       'avg(Bank Lending Rate)', 'avg(Trange)', 'avg(MOM20)',
       'avg(Balance of Trade)', 'avg(HT_TRENDLINE)', 'avg(ULTOSC)',
       'avg(Inflation Rate )', 'avg(ROC5)', 'avg(close)',
       'avg(Food Inflation)', 'avg(middleband)', 'avg(ROC10)', 'avg(volume)',
       'avg(macd1520)', 'avg(high)', 'avg(slowk)', 'diffClose'],
      dtype='object')


for company in top_companies_per_sector:
    df_log = np.log(top_companies_df[top_companies_df['company'] == company].set_index('day')['avg(sma10)'])
    train_data, test_data = df_log[3:int(len(df_log)*0.9)], df_log[int(len(df_log)*0.9):]
    model_autoARIMA = auto_arima(train_data, start_p=0, start_q=0,
                      test='adf',       # use adftest to find optimal 'd'
                      max_p=3, max_q=3, # maximum p and q
                      m=1,              # frequency of series
                      d=None,           # let model determine 'd'
                      seasonal=False,   # No Seasonality
                      start_P=0, 
                      D=0, 
                      trace=False,
                      error_action='ignore',  
                      suppress_warnings=True, 
                      stepwise=True)
    print('ARIMA Summary for {}\n: {}'.format(company,model_autoARIMA.summary()))
    model_autoARIMA.plot_diagnostics(figsize=(15,8))
    plt.title('ARIMA Plot for {}'.format(company))
    
    fc, /gateway/default/node/conf?host&port = model_autoARIMA.predict(n_periods=len(test_data), index=test_data.index, return_conf_int=True)  
    fc_series = pd.DataFrame(list(zip(fc,test_data.index)), columns=['fitted', 'date']).set_index('date')
    lower_series = pd.Series(/gateway/default/node/conf?host&port[:, 0], index=test_data.index)
    upper_series = pd.Series(/gateway/default/node/conf?host&port[:, 1], index=test_data.index)
    
    #fc = fitted.forecast(len(test_data), alpha=0.05)
    
    #fc_series = pd.DataFrame(list(zip(fc,test_data.index)), columns=['fitted', 'date']).set_index('date')
    # Plot
    plt.figure(figsize=(10,5), dpi=100)
    plt.plot(train_data, label='training data')
    plt.plot(test_data, color = 'blue', label='Actual Stock Price')
    plt.plot(fc_series, color = 'orange',label='Predicted Stock Price')
    plt.fill_between(lower_series.index, lower_series, upper_series, 
                 color='k', alpha=.10)
    plt.title('{} Stock Price Prediction'.format(company))
    plt.xlabel('Time')
    plt.ylabel('{} Stock Price'.format(company))
    plt.legend(loc='upper left', fontsize=8)
    plt.show()

ARIMA Summary for INDIGO
:                                SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                 1428
Model:               SARIMAX(1, 1, 0)   Log Likelihood                3309.273
Date:                Wed, 30 Nov 2022   AIC                          -6614.545
Time:                        04:01:58   BIC                          -6604.018
Sample:                             0   HQIC                         -6610.614
                               - 1428                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1          0.1973      0.022      9.142      0.000       0.155       0.240
sigma2         0.0006   8.11e-06     69.801      0.000       0.001       0.001
===================================================================================
Ljung-Box (L1) (Q):                   0.01   Jarque-Bera (JB):              8507.48
Prob(Q):                              0.91   Prob(JB):                         0.00
Heteroskedasticity (H):               1.14   Skew:                            -1.13
Prob(H) (two-sided):                  0.14   Kurtosis:                        14.74
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).

/opt/conda/miniconda3/lib/python3.8/site-packages/statsmodels/tsa/base/tsa_model.py:834: ValueWarning: No supported index is available. Prediction results will be given with an integer index beginning at `start`.

ARIMA Summary for ADANIENT
:                                SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                 1589
Model:               SARIMAX(3, 1, 1)   Log Likelihood                2566.643
Date:                Wed, 30 Nov 2022   AIC                          -5123.286
Time:                        04:02:11   BIC                          -5096.435
Sample:                             0   HQIC                         -5113.312
                               - 1589                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1          0.4702      0.274      1.713      0.087      -0.068       1.008
ar.L2         -0.0681      0.058     -1.169      0.242      -0.182       0.046
ar.L3          0.1014      0.035      2.864      0.004       0.032       0.171
ma.L1         -0.3077      0.276     -1.113      0.266      -0.849       0.234
sigma2         0.0023   9.76e-06    236.617      0.000       0.002       0.002
===================================================================================
Ljung-Box (L1) (Q):                   0.00   Jarque-Bera (JB):          22851976.22
Prob(Q):                              0.98   Prob(JB):                         0.00
Heteroskedasticity (H):               0.17   Skew:                           -18.79
Prob(H) (two-sided):                  0.00   Kurtosis:                       589.48
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).

/opt/conda/miniconda3/lib/python3.8/site-packages/statsmodels/tsa/base/tsa_model.py:834: ValueWarning: No supported index is available. Prediction results will be given with an integer index beginning at `start`.

ARIMA Summary for MARUTI
:                                SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                 1614
Model:               SARIMAX(1, 1, 0)   Log Likelihood                4379.565
Date:                Wed, 30 Nov 2022   AIC                          -8755.130
Time:                        04:02:15   BIC                          -8744.359
Sample:                             0   HQIC                         -8751.132
                               - 1614                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1          0.1824      0.016     11.348      0.000       0.151       0.214
sigma2         0.0003   4.03e-06     63.655      0.000       0.000       0.000
===================================================================================
Ljung-Box (L1) (Q):                   0.00   Jarque-Bera (JB):              4443.68
Prob(Q):                              0.98   Prob(JB):                         0.00
Heteroskedasticity (H):               2.08   Skew:                            -0.35
Prob(H) (two-sided):                  0.00   Kurtosis:                        11.10
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).

/opt/conda/miniconda3/lib/python3.8/site-packages/statsmodels/tsa/base/tsa_model.py:834: ValueWarning: No supported index is available. Prediction results will be given with an integer index beginning at `start`.

ARIMA Summary for BHARTIARTL
:                                SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                 1614
Model:               SARIMAX(0, 1, 1)   Log Likelihood                4191.650
Date:                Wed, 30 Nov 2022   AIC                          -8379.301
Time:                        04:02:20   BIC                          -8368.529
Sample:                             0   HQIC                         -8375.303
                               - 1614                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ma.L1          0.1206      0.021      5.632      0.000       0.079       0.163
sigma2         0.0003   7.88e-06     41.053      0.000       0.000       0.000
===================================================================================
Ljung-Box (L1) (Q):                   0.00   Jarque-Bera (JB):               328.28
Prob(Q):                              0.99   Prob(JB):                         0.00
Heteroskedasticity (H):               1.37   Skew:                             0.24
Prob(H) (two-sided):                  0.00   Kurtosis:                         5.16
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).

/opt/conda/miniconda3/lib/python3.8/site-packages/statsmodels/tsa/base/tsa_model.py:834: ValueWarning: No supported index is available. Prediction results will be given with an integer index beginning at `start`.

ARIMA Summary for BAJFINANCE
:                                SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                 1614
Model:               SARIMAX(0, 1, 1)   Log Likelihood                3830.036
Date:                Wed, 30 Nov 2022   AIC                          -7654.072
Time:                        04:02:24   BIC                          -7637.914
Sample:                             0   HQIC                         -7648.075
                               - 1614                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
intercept      0.0018      0.001      2.786      0.005       0.001       0.003
ma.L1          0.1538      0.015      9.931      0.000       0.123       0.184
sigma2         0.0005   8.09e-06     62.617      0.000       0.000       0.001
===================================================================================
Ljung-Box (L1) (Q):                   0.00   Jarque-Bera (JB):              4315.75
Prob(Q):                              0.99   Prob(JB):                         0.00
Heteroskedasticity (H):               1.70   Skew:                            -0.49
Prob(H) (two-sided):                  0.00   Kurtosis:                        10.95
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).

/opt/conda/miniconda3/lib/python3.8/site-packages/statsmodels/tsa/base/tsa_model.py:834: ValueWarning: No supported index is available. Prediction results will be given with an integer index beginning at `start`.